Bug 2356050
| Summary: | [7.1.z backport] osd/scrub: discard repair_oinfo_oid() | |||
|---|---|---|---|---|
| Product: | [Red Hat Storage] Red Hat Ceph Storage | Reporter: | Alex <amilzon> | |
| Component: | RADOS | Assignee: | Ronen Friedman <rfriedma> | |
| Status: | CLOSED ERRATA | QA Contact: | skanta | |
| Severity: | high | Docs Contact: | ||
| Priority: | unspecified | |||
| Version: | 7.1 | CC: | bhkaur, bhubbard, ceph-eng-bugs, cephqe-warriors, mcaldeir, ngangadh, nojha, rfriedma, rpollack, rsachere, tserlin, vdas, vumrao | |
| Target Milestone: | --- | |||
| Target Release: | 7.1z4 | |||
| Hardware: | Unspecified | |||
| OS: | Unspecified | |||
| Whiteboard: | ||||
| Fixed In Version: | ceph-18.2.1-309.el9cp | Doc Type: | Enhancement | |
| Doc Text: |
.PG scrub performance improved by removing unnecessary object ID repair check
Previously, every PG scrub invoked `repair_oinfo_oid()`, a function meant to fix mismatched object IDs in rare cases linked to a historical filesystem bug. This added unnecessary overhead, as the check applied only under very specific conditions.
With this enhancement, the check was removed, improving deep scrub performance by over 10%. Shallow scrubs are expected to benefit even more.
|
Story Points: | --- | |
| Clone Of: | ||||
| : | 2356515 (view as bug list) | Environment: | ||
| Last Closed: | 2025-05-07 12:49:12 UTC | Type: | Bug | |
| Regression: | --- | Mount Type: | --- | |
| Documentation: | --- | CRM: | ||
| Verified Versions: | Category: | --- | ||
| oVirt Team: | --- | RHEL 7.3 requirements from Atomic Host: | ||
| Cloudforms Team: | --- | Target Upstream Version: | ||
| Embargoed: | ||||
| Bug Depends On: | ||||
| Bug Blocks: | 2356515 | |||
|
Description
Alex
2025-03-30 09:10:02 UTC
Please specify the severity of this bug. Severity is defined here: https://bugzilla.redhat.com/page.cgi?id=fields.html#bug_severity. Hi, @Icemanny, @Ronen, here is a KCS to spread out scrubs correctly for RHCS 5/6 and RHCS 7+: https://access.redhat.com/solutions/7109348 Ronen, the specifics of scrub scheduling changed in 7+, but it does not actually spread the scrubs evenly, should I open a BZ so we can investigate that? It's explained in the KCS above and I played around with it, it's rather difficult to get a more uniform scrub scheduling and it's very clustered (well, more like a bell curve). BR Raimund Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory (Important: Red Hat Ceph Storage 7.1 security, bug fix, and enhancement updates), and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://access.redhat.com/errata/RHSA-2025:4664 The needinfo request[s] on this closed bug have been removed as they have been unresolved for 120 days |